Hidden reasoning tokens in a transformer trained on filler chain-of-thought can reportedly be recovered as rank-2 predictions during decoding.
A mathematical framework for transformer circuits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Understanding Hidden Computations in Chain-of-Thought Reasoning
Hidden reasoning tokens in a transformer trained on filler chain-of-thought can reportedly be recovered as rank-2 predictions during decoding.